Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
aqsalose
on July 18, 2017
|
parent
|
context
|
favorite
| on:
Multi-Task Learning in Atari Video Games with Emer...
They are comparing their genetic programming results with a deep learning paper published in 2015. [1]
[1]
https://www.nature.com/nature/journal/v518/n7540/abs/nature1...
phoe-krk
on July 18, 2017
[–]
What a time to live in, when papers from 2015 are "really old" in 2017.
baq
on July 18, 2017
|
parent
|
next
[–]
1 deep learning year is about 49 dog years.
amelius
on July 18, 2017
|
parent
|
prev
|
next
[–]
It highly depends on the field you're in though.
posterboy
on July 18, 2017
|
parent
|
prev
[–]
What is "exponential growth"!
sk0g
on July 18, 2017
|
root
|
parent
[–]
It's more logarithmic, isn't it? Right now we're at the beginning stage, where there's massive discoveries and changes happening, but in say, 50 years time, there won't be much changing year-to-year.
jcranberry
on July 18, 2017
|
root
|
parent
[–]
Logarithmic or logistic?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
[1] https://www.nature.com/nature/journal/v518/n7540/abs/nature1...